A deep learning system for detecting diabetic retinopathy across the disease spectrum
| Autor: | Xiaokang Yang, Chun Cai, Xuhong Hou, Shen Yaxin, Bin Sheng, Yuexing Liu, Yan Chen, Liu Ruhan, Huating Li, Xiangning Wang, Xiaoxue Long, Dinggang Shen, Yang Wen, Haidong Zou, Hong-Yu Kong, Qiang Wu, Lina Lu, Liang Wu, Weiping Jia, Ling Dai |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
medicine.medical_specialty
Image quality Fundus Oculi Science General Physics and Astronomy Datasets as Topic Fundus (eye) Severity of Illness Index General Biochemistry Genetics and Molecular Biology Article 03 medical and health sciences 0302 clinical medicine Deep Learning Diabetes complications Diabetes mellitus Ophthalmology Image Interpretation Computer-Assisted medicine Humans 030212 general & internal medicine Grading (tumors) Aged Multidisciplinary Diabetic Retinopathy Receiver operating characteristic business.industry Deep learning Disease spectrum General Chemistry Diabetic retinopathy medicine.disease Retinal diseases Diabetes Mellitus Type 2 ROC Curve 030221 ophthalmology & optometry Artificial intelligence business |
| Zdroj: | Nature Communications Nature Communications, Vol 12, Iss 1, Pp 1-11 (2021) |
| ISSN: | 2041-1723 |
| Popis: | Retinal screening contributes to early detection of diabetic retinopathy and timely treatment. To facilitate the screening process, we develop a deep learning system, named DeepDR, that can detect early-to-late stages of diabetic retinopathy. DeepDR is trained for real-time image quality assessment, lesion detection and grading using 466,247 fundus images from 121,342 patients with diabetes. Evaluation is performed on a local dataset with 200,136 fundus images from 52,004 patients and three external datasets with a total of 209,322 images. The area under the receiver operating characteristic curves for detecting microaneurysms, cotton-wool spots, hard exudates and hemorrhages are 0.901, 0.941, 0.954 and 0.967, respectively. The grading of diabetic retinopathy as mild, moderate, severe and proliferative achieves area under the curves of 0.943, 0.955, 0.960 and 0.972, respectively. In external validations, the area under the curves for grading range from 0.916 to 0.970, which further supports the system is efficient for diabetic retinopathy grading. As the leading cause of vision loss in working-age adults, diabetic retinopathy requires routinely retinal screening. Here the authors develop a deep learning system that can facilitate the screening by providing real-time image quality assessment, lesions detection, and grades across the disease spectrum. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|